A neural network based edge detector

An approach to the edge detection problem based on the nonlinear mapping and generalization capabilities of multilayer feed forward neural networks is proposed. The task of edge detection is broken into two parts, i.e., mapping typical gray levels in primitive small image blocks (e.g., 3*3 windows) to their corresponding most likely edge patterns using a simple neural network, and combining this locally derived information (including presence, orientation and strength of edge) in a consistent way. Some edge detection experiments based on this scheme are provided. The suggested scheme, because of its parallel structure, is fast and can be easily implemented using analog VLSI hardware.<<ETX>>

[1]  John F. Canny,et al.  A Computational Approach to Edge Detection , 1986, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[2]  Robert M. Haralick,et al.  Digital Step Edges from Zero Crossing of Second Directional Derivatives , 1984, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[3]  L. Moura,et al.  Edge detection through cooperation and competition , 1991, [Proceedings] 1991 IEEE International Joint Conference on Neural Networks.

[4]  Youngjin Park,et al.  Symmetric neural networks and its examples , 1992, [Proceedings 1992] IJCNN International Joint Conference on Neural Networks.

[5]  R.D. Clay,et al.  Fault tolerance training improves generalization and robustness , 1992, [Proceedings 1992] IJCNN International Joint Conference on Neural Networks.

[6]  Sim Heng Ong,et al.  Single-layer edge detector with competitive unsupervised learning , 1991, [Proceedings] 1991 IEEE International Joint Conference on Neural Networks.

[7]  Raymond L. Watrous.  Learning Algorithms for Connectionist Networks: Applied Gradient Methods of Nonlinear Optimization , 1988 .

[8]  Robert M. Haralick,et al.  Context dependent edge detection and evaluation , 1990, Pattern Recognit..

[9]  D Marr,et al.  Theory of edge detection , 1979, Proceedings of the Royal Society of London. Series B. Biological Sciences.

[10]  Harry Wechsler,et al.  Edge detection by associative mapping , 1989, Pattern Recognit..

[11]  Peter Grant,et al.  A comparison of neural network and matched filter processing for detecting lines in images , 1987 .

[12]  Gérard G. Medioni,et al.  Refining edges detected by a LoG operator , 1988, Proceedings CVPR '88: The Computer Society Conference on Computer Vision and Pattern Recognition.

[13]  Rama Chellappa,et al.  Edge Detection and Linear Feature Extraction Using a 2-D Random Field Model , 1989, IEEE Trans. Pattern Anal. Mach. Intell..